Israel-Hamas Conflict, 1 Year Later

  • Background: 10/7/2023 Hamas attacks Israel killing 1,200 people, Israel retaliates.

    • Estimated Palestinian dead ~44,000 (60% children & women).
  • Problem: Hamas Ministry of Health (MoH) reports casualties, cannot be corroborated.

  • Claim: “Women & children disproportionately killed” UN-OHCHR

  • Research Question: To what extent can open-source data be used to identify patterns in the targeting of Palestinian civilians in Gaza?

Methodology: Analyzing Casualty Incidents

Data Source: Airwars tracks civilian incidents from conflicts.

  1. Web Scrape: ~ 800 incidents (~9,000 deaths).

  2. Parse JSON: Extract incident characteristics, including geo-coordinates (65% of incidents), & store in SQLite database.

  3. Reverse Geo-coding: Supply incident coordinates to Nominatim API, return site type (school, hospital).

  4. Sentiment Analysis: Derive emotional tone from assessments. DistilRoBERTa-base, classifies text into Ekman’s 6 basic emotions.

  5. Clustering Analysis: Explore geographically civilian casualty patterns.

Results: Casualty Rate, Sentiment Analysis

  • Children more likely to be killed after adjusting for population size.
  • Sadness is the prominent emotional tone, followed by fear, varies across time.

Results: Hierarchical Clustering

  • Cannot discern patterns in the targeting of civilians.

    • 3-cluster model: Cluster 3 contained high average deaths from airstrikes associated w/ fear & anger, & occurred at schools & hospitals.